{
  "best_metric": 0.8977843523025513,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.33178500331785005,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006635700066357001,
      "eval_loss": 1.6524497270584106,
      "eval_runtime": 277.7049,
      "eval_samples_per_second": 9.139,
      "eval_steps_per_second": 2.287,
      "step": 1
    },
    {
      "epoch": 0.033178500331785,
      "grad_norm": 4.862736701965332,
      "learning_rate": 0.0001015,
      "loss": 1.1024,
      "step": 50
    },
    {
      "epoch": 0.06635700066357,
      "grad_norm": 3.397765874862671,
      "learning_rate": 0.000203,
      "loss": 0.9776,
      "step": 100
    },
    {
      "epoch": 0.099535500995355,
      "grad_norm": 3.8949413299560547,
      "learning_rate": 0.0001952737725498956,
      "loss": 0.9883,
      "step": 150
    },
    {
      "epoch": 0.13271400132714,
      "grad_norm": 3.1730785369873047,
      "learning_rate": 0.00017327133829043458,
      "loss": 0.9864,
      "step": 200
    },
    {
      "epoch": 0.16589250165892502,
      "grad_norm": 3.8219852447509766,
      "learning_rate": 0.00014034236838505662,
      "loss": 0.9579,
      "step": 250
    },
    {
      "epoch": 0.19907100199071,
      "grad_norm": 2.870953321456909,
      "learning_rate": 0.0001015,
      "loss": 0.9547,
      "step": 300
    },
    {
      "epoch": 0.23224950232249503,
      "grad_norm": 2.235758066177368,
      "learning_rate": 6.265763161494339e-05,
      "loss": 0.9333,
      "step": 350
    },
    {
      "epoch": 0.26542800265428,
      "grad_norm": 3.720842123031616,
      "learning_rate": 2.972866170956543e-05,
      "loss": 0.9269,
      "step": 400
    },
    {
      "epoch": 0.298606502986065,
      "grad_norm": 4.082036018371582,
      "learning_rate": 7.726227450104397e-06,
      "loss": 0.9252,
      "step": 450
    },
    {
      "epoch": 0.33178500331785005,
      "grad_norm": 2.08194637298584,
      "learning_rate": 0.0,
      "loss": 0.89,
      "step": 500
    },
    {
      "epoch": 0.33178500331785005,
      "eval_loss": 0.8977843523025513,
      "eval_runtime": 276.4895,
      "eval_samples_per_second": 9.179,
      "eval_steps_per_second": 2.297,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.544453535702712e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}